[Docs] Replace rst style double-backtick with md single-backtick (#27091)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/model_executor/models/olmo.py

@@ -64,7 +64,7 @@ from .utils import (
 class OlmoAttention(nn.Module):
     """
     This is the attention block where the output is computed as
-    ``Attention(LN(x))`` in ``MLP(LN(x + Attention(LN(x))))``
+    `Attention(LN(x))` in `MLP(LN(x + Attention(LN(x))))`
     (plus another skip connection).
     """
 
@@ -144,7 +144,7 @@ class OlmoAttention(nn.Module):
 class OlmoMLP(nn.Module):
     """
     This is the MLP block where the output is computed as
-    ``MLP(LN(x))`` in ``MLP(LN(x + Attention(LN(x))))``
+    `MLP(LN(x))` in `MLP(LN(x + Attention(LN(x))))`
     (plus another skip connection).
     """
 
@@ -193,7 +193,7 @@ class OlmoMLP(nn.Module):
 class OlmoDecoderLayer(nn.Module):
     """
     This is a typical transformer block where the output is
-    computed as ``MLP(LN(x + Attention(LN(x))))``
+    computed as `MLP(LN(x + Attention(LN(x))))`
     (plus another skip connection).
     """